bart_fine_tuned_0.99_epochs_rouge2_0.119

README.md

@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the scientific_papers dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.1064
-- Rouge2 Precision: 0.1576
-- Rouge2 Recall: 0.1324
-- Rouge2 Fmeasure: 0.142
+- Loss: 2.6842
+- Rouge2 Precision: 0.1282
+- Rouge2 Recall: 0.1133
+- Rouge2 Fmeasure: 0.1186
 
 ## Model description
 
@@ -53,7 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
 |:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
-| 2.9388        | 0.53  | 10   | 3.1913          | 0.139            | 0.116         | 0.1248          |
+| 2.9888        | 0.32  | 10   | 2.8091          | 0.1445           | 0.1158        | 0.1251          |
+| 2.7186        | 0.64  | 20   | 2.6898          | 0.1332           | 0.1183        | 0.1232          |
+| 2.6847        | 0.96  | 30   | 2.6861          | 0.1291           | 0.1144        | 0.1197          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39b87a40f3d7fac608e05069f034858e5aafd689f62727463954d7e3c0232c1c
+oid sha256:826c6b513f509b7d690f09065bb436e8259f7cad9191d0dcb2a0b67e208eec5c
 size 1625422896

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930aeab3efe26406cca9de406e803b2686856aaf595a107966b5e25d99d51a56
+oid sha256:0de39d356cf60c5cb88a82e8a9e176ae5f8fe2ffdcbb897b51ff8b1ed5e70ee2
 size 4347